Calculate the cost of using rerank-3-lite from Voyage for your AI applications
Pricing data last updated:
Mode: Rerank
Built for enterprise-grade reliability, governance, and scale. Deploy in seconds.
rerank-3-lite is a rerank model from Voyage, one of 6 rerank models they offer. It is priced at $0.02 per 1M input tokens and $0.0000 per 1M output tokens, ranking 4 out of 10 rerank models by cost and cheaper than 60% of models in this category. It accepts up to 32K input tokens.
Note: Use the interactive calculator above to estimate costs for your specific usage patterns.
Use the maximum token limits shown above to understand the model's capacity. This model can handle up to 32,000 input tokens. The maximum output length is 32,000 tokens.
At $0.02 per 1M input tokens and $0.0000 per 1M output tokens, rerank-3-lite ranks 4 out of 10 rerank models by input cost. It is more affordable compared to the median of $0.05 for rerank models, and is cheaper than 60% of models in this category.
| Model | Provider | Input / 1M tokens | Output / 1M tokens | vs rerank-3-lite |
|---|---|---|---|---|
| bge-reranker-v2-m3 | Novita | $0.01 | $0.01 | -50% |
| jina-reranker-v2-base-multilingual | Jina AI | $0.05 | $0.0000 | +150% |
| qwen3-reranker-8b | Fireworks AI | $0.20 | $0.0000 | +900% |
Similar rerank models from other providers
No. rerank-3-lite costs $0.02 per 1M input tokens while bge-reranker-v2-m3 costs $0.01 per 1M input tokens, making bge-reranker-v2-m3 50% more affordable for input. However, rerank-3-lite may offer different capabilities or performance characteristics that justify the price difference.
rerank-3-lite input pricing is $0.02 per 1M tokens, which is 60% below the median of $0.05 for rerank models. It ranks 4 out of 10 rerank models by input cost, making it cheaper than 60% of models in this category. For output, it costs $0.0000 per 1M tokens compared to the median of $0.03.
Among Voyage's 6 rerank models, rerank-3-lite ranks 3 by input cost.
The most comparable rerank models to rerank-3-lite are: bge-reranker-v2-m3 from Novita ($0.01/1M input tokens); jina-reranker-v2-base-multilingual from Jina AI ($0.05/1M input tokens); qwen3-reranker-8b from Fireworks AI ($0.20/1M input tokens); qwen3-reranker-8b from Novita ($0.05/1M input tokens). These alternatives were selected based on similar capabilities, pricing, and provider diversity. You can compare any of these models in detail using the Bifrost Model Library.
rerank-3-lite is priced based on input and output tokens. Use the interactive calculator at the top of this page to estimate costs for your specific workload. Enter your expected input and output tokens volume and the calculator will show the total cost breakdown. For reference, processing 1M input tokens costs $0.02 and generating 1M output tokens costs $0.0000.